JP2019142286A - Parking assistance device - Google Patents

Abstract

To provide a parking assistance device that is able to park a vehicle in a target position by traveling it along an appropriate travel path.SOLUTION: A parking assistance device (13) comprises: learning means (131) that learns a specific position (WP_shift), which is the position of a vehicle at a point in time when behavior of the vehicle (1) satisfies a specific condition during a period of time when a parking operation is performed by a driver; setting means (132) that sets a via-point (WP_transit) within a first predetermined range (CA) including a specific position learned by the learning means; and generation means (132) that generates, as a target path (TR_target), a first travel path that reaches a target position (WP_end) via the via-point set by the setting means. The setting means sets a via-point on the basis of a first evaluation score (SC2) of a first travel path, which is determined according to at least a curvature change rate of the first travel path and/or a distance between the first travel path and a first obstacle.SELECTED DRAWING: Figure 6

Description

  The present invention relates to a technical field of a parking assistance apparatus capable of performing parking assistance for automatically parking a vehicle at a target position.

  Patent Document 1 describes a specific example of a parking assistance device. Specifically, the parking assistance device described in Patent Literature 1 can operate in two modes, a learning mode and an operation mode. The parking assist device that operates in the learning mode is configured such that the vehicle moves between a reference start position where the vehicle starts to move to a parking position where the vehicle is parked while the vehicle is parked in a parking space (for example, a garage) by a driver's operation. Learn the reference route that you drove. The parking assistance device that operates in the operation mode automatically parks the vehicle in the parking space where the vehicle is parked in the learning mode, using the learning result in the learning mode. As a result, the vehicle is parked at the same parking position as the parking position where the vehicle is parked in the parking space in the learning mode.

  Other prior art documents relating to the present invention include Patent Documents 2 and 3.

JP 2013-530867 A JP 2011-141854 A JP 2008-536734 A

  In order to automatically park the vehicle in the parking space, the parking assist device described in Patent Document 1 is a reference route on which the vehicle travels from a reference start position where the vehicle starts to a parking position where the vehicle is parked. Learning. However, the driver's operation may include a useless operation (for example, an operation of turning the steered wheels too much). For this reason, the driver's useless operation may be reflected in the reference route learned by the parking assist device in the learning mode. Therefore, when the parking assistance apparatus described in Patent Document 1 automatically parks the vehicle in the parking space, there is a possibility that the vehicle is controlled to travel on an inappropriate travel route. That is, there is a possibility that the parking assistance device described in Patent Literature 1 cannot travel the appropriate travel route and park the vehicle in the parking space.

  This invention makes it a subject to provide the parking assistance apparatus which can drive | work an appropriate driving | running route and can park a vehicle in a target position.

  One aspect of the parking assist device of the present invention is a specific position that is a position of the vehicle when a behavior of the vehicle satisfies a specific condition during a period in which a driver performs a parking operation for parking the vehicle. Learning means for learning, setting means for setting a via position within a first predetermined range including the specific position learned by the learning means, and the vehicle parked via the via position set by the setting means Generating means for generating, as a target route that the vehicle should pass when the vehicle is automatically parked at the target position, the setting means includes: The first travel route determined in accordance with at least a curvature change rate of the first travel route and / or a distance between the first travel route and a first obstacle existing around the first travel route. 1 evaluation Based on A, it sets the through position.

FIG. 1 is a block diagram illustrating a configuration of a vehicle according to the present embodiment. FIG. 2 is a flowchart showing the flow of the learning operation of the present embodiment. FIG. 3 is a plan view showing the distance between the travel route and the obstacle. FIG. 4 is a map showing the relationship between the integrated value of the distance between the travel route and the obstacle and the score component. Each of FIG. 5A and FIG. 5B is a plan view showing a travel route on which the vehicle actually travels when the vehicle is parked in the parking space by the driver's parking operation. FIG. 6 is a flowchart showing the flow of the parking assist operation of the present embodiment. FIG. 7 is a plan view showing a plurality of candidate waypoints. FIG. 8 is a plan view showing a travel route on which the vehicle actually travels when the vehicle is parked in the parking space by the driver's parking operation. FIG. 9 is a plan view showing a target route generated by the parking assistance unit of the present embodiment. FIG. 10 is a flowchart showing the flow of the learning operation in the first modification. FIG. 11 is a flowchart showing a flow of operations for specifying a straight travel start waypoint and a straight travel end waypoint. Each of FIG. 12A to FIG. 12E is a graph showing the curvature of the travel route on which the vehicle actually travels when the vehicle is parked in the parking space by the driver's parking operation. FIG. 13 is a plan view showing the straight travel start waypoint and the straight travel end waypoint in association with the travel route on which the vehicle has actually traveled when the vehicle is parked in the parking space by the driver's parking operation. FIG. 14 is a flowchart showing a flow of the parking support operation in the first modification. FIG. 15A is a plan view showing a vehicle traveling off the target route, and FIG. 15B is a plan view showing a newly generated target route.

  Hereinafter, an embodiment of a parking assistance device will be described with reference to the drawings. Below, description is advanced using the vehicle 1 by which embodiment of the parking assistance apparatus was mounted.

(1) Configuration of Vehicle 1 First, the configuration of the vehicle 1 of the present embodiment will be described with reference to FIG. As shown in FIG. 1, the vehicle 1 includes an outside world detection device 11, an inside world detection device 12, and an ECU (Electrical Control Unit) 13, which is a specific example of a “parking support device” described later.

  The external environment detection device 11 is a detection device that detects an external situation of the vehicle 1. The external situation may include, for example, a situation around the vehicle 1 (so-called traveling environment). The external environment detection device 11 includes, for example, at least one of a camera, a radar, and a rider (LIDAR: Light Detection and Ranging).

  The inner world detection device 12 is a detection device that detects an internal state of the vehicle 1. The internal situation may include, for example, the traveling state of the vehicle 1. The internal situation may include, for example, operating states of various devices included in the vehicle 1. The inner world detection sensor 12 is, for example, a vehicle speed sensor that detects the vehicle speed of the vehicle 1, a shift position sensor that detects the gear range (that is, shift position) of the vehicle 1, and a steering angle that detects the steering angle of the steering wheel provided in the vehicle 1. Including at least one of a sensor, a turning angle sensor for detecting a turning angle of a turning wheel included in the vehicle 1, and a position sensor (for example, a GPS (Global Positioning System) sensor) for detecting the position of the vehicle 1. .

  The ECU 13 controls the overall operation of the vehicle 1. In this embodiment, in particular, when the driver parks the vehicle 1 in the desired parking space SP, the ECU 13 determines the position of the vehicle 1 when the behavior of the vehicle 1 satisfies a specific condition as a waypoint. (Way Point) A learning operation for learning as WP is performed. Further, the ECU 13 performs a parking support operation for automatically parking the vehicle 1 in a desired parking space SP based on the waypoint WP learned by the learning operation.

  In order to perform the learning operation, the ECU 13 includes a learning unit 131 which is a specific example of “learning means” in an appendix to be described later as a processing block logically realized in the ECU 13. The learning unit 131 includes a waypoint learning unit 1311 (hereinafter, the waypoint learning unit 1311 is referred to as a “WP learning unit 1311”) and a waypoint storage as processing blocks that are logically realized inside the learning unit 131. Unit 1312 (hereinafter, the waypoint storage unit 1312 is referred to as “WP storage unit 1312”). Further, in order to perform the parking support operation, the ECU 13 includes a parking support unit 132 as a processing block that is logically realized inside the ECU 13. The parking support unit 132 is a specific example of each of an information acquisition unit 1321 and a “setting unit” and “generation unit” in an appendix to be described later as processing blocks that are logically realized inside the parking support unit 132. A route generation unit 1322 and a vehicle control unit 1323 are provided. The operations of the learning unit 131 and the parking support unit 132 will be described in detail later with reference to FIG.

(2) Operation of ECU 13 Subsequently, a learning operation and a parking support operation performed by the ECU 13 will be described in order.

(2-1) Flow of Learning Operation First, the flow of the learning operation of this embodiment will be described with reference to FIG. FIG. 2 is a flowchart showing the flow of the learning operation of the present embodiment.

  As shown in FIG. 2, the learning unit 131 determines whether or not the driver requests execution of a learning operation (step S11). Specifically, the learning unit 131 determines whether or not the driver is operating an operation device provided in the vehicle 1 (particularly, an operation device that can be operated by the driver to request execution of the learning operation). When the driver is operating the controller device, the learning unit 131 determines that the driver requests execution of the learning operation. The learning operation is performed when the driver performs a parking operation for parking the vehicle 1 in the desired parking space SP. For this reason, the driver typically requests execution of a learning operation before starting the parking operation.

  As a result of the determination in step S11, when it is determined that the driver does not request execution of the learning operation (step S11: No), the learning unit 131 ends the learning operation illustrated in FIG. When the learning operation illustrated in FIG. 2 is completed, the learning unit 131 starts the learning operation illustrated in FIG. 2 again after the first predetermined period has elapsed.

  On the other hand, as a result of the determination in step S11, when it is determined that the driver requests execution of the learning operation (step S11: Yes), the WP learning unit 1311 parks the vehicle 1 by the driver's parking operation. During this period, detection information that is a detection result of the external detection device 11 and the internal detection device 12 is acquired (step S12). Considering that the learning operation is performed while the vehicle 1 is parked by the driver's parking operation, the process of step S12 is repeatedly performed in parallel with the processes of step S13 to step S15 described later. .

  Thereafter, the WP learning unit 1311 learns the position of the vehicle 1 (that is, the parking start position) at the parking start timing at which the driver started the parking operation as the start waypoint WP_start based on the detection information acquired in step S12. (Step S13). The parking start timing may be a timing at which the driver requests execution of the learning operation. Alternatively, the parking start timing may be a timing at which the vehicle 1 starts to move (that is, a timing at which the vehicle speed of the vehicle 1 has changed from zero to a value greater than zero). Alternatively, the parking start timing is a range that is used when the vehicle 1 is traveling from a range (for example, P range or N range) that is used when the vehicle 1 is stopped. The timing may be switched to (for example, D range or R range). For convenience of explanation, in the present embodiment, it is assumed that the parking start timing is a timing when the gear range of the vehicle 1 is switched from the P range or the N range to the D range. That is, in this embodiment, the driver is assumed to park the vehicle 1 in the parking space SP by moving the vehicle 1 forward from the parking start position.

  Furthermore, the WP learning unit 1311 determines the position of the vehicle 1 at the shift switching timing when the driver switches the gear range in order to change the traveling direction of the vehicle 1 after the parking operation is started based on the detection information acquired in step S12. (That is, the shift switching position) is learned as the shift switching waypoint WP_shift (step S14). The shift switching timing is such that the gear range is changed from a range in which the vehicle 1 is moved forward (for example, D range) to a range in which the vehicle 1 is moved backward (for example, R range) or from a range in which the vehicle 1 is moved backward. It is the timing that was switched. For convenience of explanation, in this embodiment, it is assumed that the shift switching timing is the timing when the gear range of the vehicle 1 is switched from the D range to the R range. In other words, in the present embodiment, the driver moves the vehicle 1 forward from the parking start position and moves it to an appropriate position, and then moves the vehicle 1 backward to park the vehicle 1 in the parking space SP.

  Further, the WP learning unit 1311 learns the position of the vehicle 1 at the parking completion timing when the driver completes the parking operation (that is, the parking completion position) as the completed waypoint WP_end based on the detection information acquired in step S12. (Step S15). The parking completion timing may be a timing at which the driver requests the end of the learning operation. Alternatively, the parking completion timing may be a timing when a certain time has elapsed since the vehicle 1 stopped (that is, a timing when a certain time has elapsed since the vehicle speed of the vehicle 1 changed from a value greater than zero to zero). . Alternatively, the parking completion timing is the timing when the gear range of the vehicle 1 is switched from the range used when the vehicle 1 is traveling to the range used when the vehicle 1 is stopped. Good. For convenience of explanation, in the present embodiment, it is assumed that the parking completion timing is a timing when the gear range of the vehicle 1 is switched from the R range to the P range.

  Thereafter, the WP learning unit 1311 includes waypoint information (hereinafter, the waypoint information is referred to as “WP information”) including an information set of the learned start waypoint WP_start, shift switching waypoint WP_shift, and completion waypoint WP_end. The data is stored in the WP storage unit 1312. In order to store the WP information in the WP storage unit 1322, the WP learning unit 1311 first determines whether or not the WP information acquired in the past is already stored in the WP storage unit 1312 (step S16). Specifically, the WP learning unit 1311 includes a start waypoint WP_start and a complete waypoint WP_end that respectively match or are close to the start waypoint WP_start and the completion waypoint WP_end newly acquired by the learning operation performed this time. It is determined whether WP information is already stored in the WP storage unit 1312. The WP information including the start waypoint WP_start and the completion waypoint WP_end that respectively coincide with or close to the start waypoint WP_start and the completion waypoint WP_end newly acquired by the learning operation performed this time is already stored in the WP storage unit 1312. In the case where the WP information has been acquired, the WP learning unit 1311 determines that WP information acquired in the past is stored in the WP storage unit 1312.

  As a result of the determination in step S16, when it is determined that WP information acquired in the past is not stored in the WP storage unit 1312 (step S16: No), the WP learning unit 1311 performs the learning operation performed this time. The WP storage unit 1312 stores the new WP information including the start waypoint WP_start, the shift switching waypoint WP_shift, and the completion waypoint WP_end that are newly acquired in step S18.

  On the other hand, when it is determined that WP information acquired in the past is stored in the WP storage unit 1312 (step S16: Yes), the WP learning unit 1311 stores the WP information already stored (hereinafter, as appropriate). Either the “old WP information” or the WP information newly acquired by the learning operation performed this time (hereinafter referred to as “new WP information”) is stored in the WP storage unit 1312 (step S17). . In order to determine which of the old WP information and the new WP information is stored in the WP storage unit 1312, the WP learning unit 1311 calculates an evaluation score SC1 for each of the old WP information and the new WP information.

  The evaluation score SC1 is a quantitative index value indicating the optimality (in other words, the goodness or appropriateness) of the travel route TR_actual on which the vehicle 1 has actually traveled by the parking operation. When the travel route TR_actual is appropriate, the possibility that the parking operation was appropriate is relatively high. Therefore, it can be said that the evaluation score SC1 is a quantitative index value indicating the optimum degree of the parking operation performed by the driver. In the following description, for the convenience of description, it is assumed that the evaluation score SC1 is defined so that the evaluation score SC1 becomes smaller as the travel route TR_actual becomes appropriate.

  The evaluation score SC1 is an index value determined according to the curvature change rate of the travel route TR_actual. Specifically, the evaluation score SC1 is, for example, an index value determined from the viewpoint that the travel route TR_actual is more appropriate as the curvature change rate of the travel route TR_actual is smaller. This is because it is estimated that the smaller the curvature change rate, the smoother the driver's steering (as a result, the smaller the steering actuator load when such smooth steering is realized by the parking assist operation). Because. In the present embodiment, the evaluation score SC1 includes a score component SC1a that decreases as the curvature change rate of the travel route TR_actual decreases. In order to calculate the score component SC1a, the WP learning unit 1311 calculates the rate of curvature change per unit time or per unit travel distance based on the detection information acquired in step S12. For example, the WP learning unit 1311 may specify the travel route TR_actual from the detection information and calculate the curvature change rate from the identified travel route TR_actual. Alternatively, the WP learning unit 1311 has parameters of the vehicle 1 that have a correlation with the curvature change rate (for example, at least one of the steering angle of the steering wheel, the turning angle of the steered wheels, the deflection angle of the vehicle 1, and the yaw rate of the vehicle 1). Based on the above, the curvature change rate may be calculated. Thereafter, the WP learning unit 1311 integrates the calculated curvature change rate (in particular, the absolute value or the square value thereof) over the entire travel route TR_actual. The integral value of the curvature change rate calculated in this way becomes the score component SC1a. One of the reasons for using the absolute value or the square value of the curvature change rate is to eliminate the influence of the difference in the sign of the curvature change rate. However, the WP learning unit 1311 may calculate the score component SC1a by other methods as long as the score component SC1a that becomes smaller as the curvature change rate becomes smaller can be calculated.

  The evaluation score SC1 is an index value determined according to the distance between the travel route TR_actual and an obstacle existing around the travel route TR_actual (that is, an object that obstructs the travel of the vehicle 1), for example. Specifically, the evaluation score SC1 is, for example, an index value determined from the viewpoint that the travel route TR_actual is more suitable as the distance between the travel route TR_actual and the obstacle becomes larger. This is because it is estimated that the greater the distance between the travel route TR_actual and the obstacle, the smaller the possibility that the vehicle 1 will come into contact with the obstacle. In the present embodiment, the evaluation score SC1 includes a score component SC1b that decreases as the distance between the travel route TR_actual and the obstacle increases. In order to calculate the score component SC1b, the WP learning unit 1311 calculates the distance D_P between the specific point P on the travel route TR_actual and the obstacle based on the detection information acquired in step S12. The distance D_P between the specific point P and the obstacle means the sum of the distances D between the plurality of end points j of the vehicle 1 located at the specific point P and the obstacle. For example, as shown in FIG. 3, when eight end points j (1) to j (8) are set as the end points j of the vehicle 1, the WP learning unit 1311 sets the end point j (1) as Distance D (1) between the obstacle, distance D (2) between the end point j (2) and the obstacle, ..., distance D between the end point j (8) and the obstacle The sum total with (8) is calculated. When there are a plurality of obstacles, the WP calculation unit 1311 calculates the sum of the distances between the specific point P and each of the plurality of obstacles as the distance D_P. Thereafter, the WP learning unit 1311 integrates the calculated distance D_P over the entire travel route TR_actual. That is, the WP learning unit 1311 calculates the distance D_P while moving the specific point P along the travel route TR_actual, and integrates the calculated distance D_P. Thereafter, the WP learning unit 1311 calculates the score component SC1b based on the integrated value of the distance D_P. For example, as shown in FIG. 4, the WP learning unit 1311 calculates the score component SC1b based on a map that defines the relationship between the integrated value of the distance D_P and the score component SC1b. 4 shows that (i) when the integrated value of the distance D_P is not less than the threshold Dismin and not more than the threshold Dismax (threshold Dismax> threshold Dismin), the score component SC1b increases as the integrated value of the distance D_P increases. (Ii) When the integral value of the distance D_P is less than the threshold value Dismin, the score component SC1b is constant regardless of the integral value of the distance D_P (specifically, the integral value of the distance D_P is the threshold value Dismin). (Iii) when the integrated value of the distance D_P is larger than the threshold Dismax, the score component SC1b becomes constant regardless of the integrated value of the distance D_P (specifically, (The score component SC1b is fixed when the integral value of the distance D_P matches the threshold value Dismax) It is. However, the WP learning unit 1311 may calculate the score component SC1b by other methods as long as the score component SC1b that decreases as the distance between the travel route TR_actual and the obstacle increases. Good.

  The evaluation score SC1 is an index value determined according to, for example, the number of turnovers performed during the period in which the vehicle 1 travels the travel route TR_actual (that is, the number of times the driver turns the steering wheel). Specifically, the evaluation score SC1 is, for example, an index value that is determined from the viewpoint that the travel route TR_actual is appropriate as the number of times of turn-back decreases. This is because it is estimated that the smaller the number of turnovers, the shorter the time required for parking the vehicle 1 (that is, the vehicle 1 can be parked smoothly (in other words, efficiently)). Furthermore, it is estimated that the smaller the number of turn-backs, the smoother the driver's steering (as a result, the smaller the load on the steering actuator when such smooth steering is realized by the parking assist operation). It is. In the present embodiment, the evaluation score SC1 includes a score component SC1c that decreases as the number of times of turn-back decreases. In order to calculate the score component SC1c, the WP learning unit 1311 calculates the number of times of turnover during the period in which the vehicle 1 is traveling on the travel route TR_actual based on the detection information acquired in step S12. For example, the WP learning unit 1311 may calculate the number of times of turning back based on at least one of the turning angle of the steered wheels and the steering angle of the steering wheel. The calculated number of times of switching may be used as it is as the score component SC1c.

  The evaluation score SC1 is an index value determined according to, for example, the length of the travel route TR_actual (that is, the distance traveled by the vehicle 1 before the parking in the parking space SP is completed). Specifically, the evaluation score SC1 is an index value determined from the viewpoint that the shorter the travel route TR_actual is, the more appropriate the travel route TR_actual is. This is because it is estimated that the shorter the travel route TR_actual, the shorter the time required for parking the vehicle 1. In the present embodiment, the evaluation score SC1 includes a score component SC1d that becomes smaller as the travel route TR_actual becomes shorter. In order to calculate the score component SC1d, the WP learning unit 1311 calculates the length of the travel route TR_actual (that is, the distance traveled by the vehicle 1) based on the detection information acquired in step S12. For example, the WP learning unit 1311 may calculate the length of the travel route TR_actual based on the vehicle speed of the vehicle 1. The calculated length of the travel route TR_actual may be used as it is as the score component SC1d.

  The WP learning unit 1311 calculates the evaluation score SC1 by multiplying the calculated score components SC1a to SC1d by the weighting coefficients w1a to w1d and adding them. That is, the WP learning unit 1311 calculates the evaluation score SC1 based on the mathematical formula SC1 = SC1a × w1a + SC1b × w1b + SC1c × w1c + SC1d × w1d. The weighting factors w1a to w1d are any of the curvature change rate of the travel route TR_actual, the distance between the travel route TR_actual and the obstacle, the number of turnovers, and the length of the travel route TR_actual when determining the optimum degree of the travel route TR_actual. It is set from the viewpoint of emphasizing Typically, the weighting coefficient corresponding to the parameter to be emphasized is set to a relatively large value. For example, when the curvature change rate of the travel route TR_actual is important, the weighting coefficient w1a is set to a relatively large value. The weighting factors w1a to w1d may be set in advance when the ECU 13 is installed, may be set by the ECU 13, or may be set by a driver. However, the weighting factors w1a to w1d may not be used.

  In this way, the WP learning unit 1311 calculates the evaluation score SC1 for the travel route TR_actual corresponding to the old WP information and the travel route TR_actual corresponding to the new WP information. However, the evaluation score SC1 of the travel route TR_actual corresponding to the old WP information may be included in the old WP information. In this case, the WP learning unit 1311 evaluates the evaluation score of the travel route TR_actual corresponding to the old WP information. Instead of calculating SC1 anew, it may be acquired from the old WP information.

  Thereafter, the WP learning unit 1311 determines which of the evaluation score SC1 of the travel route TR_actual corresponding to the new WP information and the evaluation score SC1 of the travel route TR_actual corresponding to the old WP information is smaller (that is, the minimum). When the evaluation score SC1 of the travel route TR_actual corresponding to the new WP information is smaller than the evaluation score SC1 of the travel route TR_actual corresponding to the old WP information, the WP learning unit 1311 stores the new WP information in the WP storage unit 1312. Remember. On the other hand, when the evaluation score SC1 of the travel route TR_actual corresponding to the new WP information is larger than the evaluation score SC1 of the travel route TR_actual corresponding to the old WP information, the WP learning unit 1311 stores the old WP information in the WP storage. The information is continuously stored in the unit 1312. That is, the WP learning unit 1311 causes the WP storage unit 1312 to store WP information having a smaller evaluation score SC1 (that is, the smallest). At this time, the WP learning unit 1311 may cause the WP storage unit 1312 to store WP information that further includes the calculated evaluation score SC1.

  An example of the travel route TR_actual is shown in FIGS. 5 (a) and 5 (b). FIG. 5A shows a travel route TR_actual # 1 having a relatively large curvature change rate, a relatively large number of times of switching, and a relatively long length. On the other hand, in FIG. 5B, the curvature change rate is relatively small, the number of times of turnover is relatively small, and the length thereof is smaller than that of the travel route TR_actual # 1 shown in FIG. A relatively short traveling route TR_actual # 2 is shown. In this case, the evaluation score SC1 of the travel route TR_actual # 2 is smaller than the evaluation score SC1 of the travel route TR_actual # 1. As a result, either the new WP information or the old WP information is WP information corresponding to the travel route TR_actual # 1, and either the new WP information or the old WP information corresponds to the travel route TR_actual # 2. In the case of WP information, the WP learning unit 1311 causes the WP storage unit 1312 to store WP information corresponding to the travel route TR_actual # 2. That is, the WP learning unit 1311 causes the WP storage unit 1312 to store WP information including the start waypoint WP_start # 2, the shift switching waypoint WP_shift # 2, and the completion waypoint WP_end # 2 corresponding to the travel route TR_actual # 2. .

(2-2) Flow of Parking Support Operation Next, the flow of the parking support operation of this embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing the flow of the parking assist operation of the present embodiment.

  As shown in FIG. 6, the parking assistance unit 132 determines whether or not the driver requests execution of the parking assistance operation (step S21). Specifically, the parking support unit 132 determines whether or not the driver is operating an operation device provided in the vehicle 1 (particularly, an operation device that can be operated by the driver to request execution of the parking support operation). . When the driver is operating the operating device, the parking assistance unit 132 determines that the driver is requesting execution of the parking assistance operation.

  As a result of the determination in step S21, when it is determined that the driver does not request execution of the parking assistance operation (step S21: No), the parking assistance unit 132 ends the parking assistance operation illustrated in FIG. When the parking support operation illustrated in FIG. 6 is completed, the parking support unit 132 starts the parking support operation illustrated in FIG. 6 again after the second predetermined period has elapsed.

  On the other hand, as a result of the determination in step S21, when it is determined that the driver is requesting execution of the parking assistance operation (step S21: Yes), the information acquisition unit 1321 is stored in the WP storage unit 1312. WP information is acquired (step S22). In particular, the information acquisition unit 1321 acquires WP information including the completed waypoint WP_end that matches or is close to the position of the parking space SP where the vehicle 1 should be parked by the parking support operation performed this time.

  Thereafter, the route generation unit 1322 sets the wayway point WP_transit that the vehicle 1 traveling by the parking assistance operation should pass through based on the shift switching waypoint WP_shift included in the WP information acquired in step S22 (step S23). ). Specifically, as illustrated in FIG. 7, the route generation unit 1322 includes a plurality of candidates for via waypoints WP_transit in a predetermined area CA including the shift switching waypoints WP_shift included in the WP information acquired in step S22. Candidate waypoints WP_candidate are set. At this time, the route generation unit 1322 may set a plurality of candidate waypoints WP_candidate that are evenly distributed in the predetermined area CA. Alternatively, the route generation unit 1322 is located in a local or random region in which a target route TR_target described later is assumed to be favorable (for example, an evaluation score SC2 described later increases correspondingly) in the predetermined region CA. A plurality of candidate waypoints WP_candidate to be distributed or distributed may be set. The route generation unit 1322 selects any one of the plurality of candidate waypoints WP_candidate as the wayway point WP_transit.

  A larger number of candidate waypoints WP_candidate can be set in the predetermined area CA as the predetermined area CA becomes wider. Therefore, there is a relatively high possibility that the optimal waypoint WP_transit can be set. On the other hand, the larger the predetermined area CA, the greater the processing load on the route generation unit 1322 for selecting any one of the plurality of candidate waypoints WP_candidate as the wayway point WP_transit. For this reason, the predetermined area CA is set to an appropriate size in consideration of a trade-off between the merit of setting the optimal waypoint WP_transit and the disadvantage of increasing the processing load of the route generation unit 1322. Also good.

  In order to select any one of the plurality of candidate waypoints WP_candidate as the wayway point WP_transit, the route generation unit 1322 calculates an evaluation score SC2 for each of the plurality of candidate waypoints WP_candidate. The evaluation score SC2 is obtained from the start waypoint WP_start included in the WP information acquired in step S22 or the current position of the vehicle 1 via the candidate waypoint WP_candidate, and the completed waypoint WP_end included in the WP information acquired in step S22. It is a quantitative index value indicating the optimum degree (in other words, goodness or appropriateness) of the travel route TR_candidate that reaches As will be described later, the route generation unit 1322 generates, as a target route TR_target, a travel route that reaches the completion waypoint WP_end from the start waypoint WP_start or the current position of the vehicle 1 via the wayway WP_transit. For this reason, the travel route TR_candidate corresponds to a candidate for the target route TR_target.

  Evaluation score SC2 is different from evaluation score SC1 described above, which is an index value indicating the optimum degree of travel route TR_actual, in that it is an index value indicating the optimum degree of travel route TR_candidate. Other features of the evaluation score SC2 are the same as the other features of the evaluation score SC1 described above. That is, the description regarding the evaluation score SC1 described above is substantially the description regarding the evaluation score SC2 by replacing the term “travel route TR_actual” with the term “travel route TR_candidate”. For this reason, for example, the route generation unit 1322 has a score component SC2a that decreases as the curvature change rate of the travel route TR_candidate decreases, and the distance between the travel route TR_candidate and the obstacle present around the travel route TR_candidate increases. From the score component SC2b, the score component SC2c, the score component SC2c that decreases as the number of times of turn-back in the vehicle 1 traveling on the travel route TR_candidate decreases, and the score component SC2d that decreases as the travel route TR_candidate decreases, An evaluation score SC2 is calculated based on w2d. That is, the path generation unit 1322 calculates the evaluation score SC2 based on the mathematical formula SC2 = SC2a × w2a + SC2b × w2b + SC2c × w2c + SC2d × w2d. The weighting coefficients w2a to w2d used in the parking assistance operation are the same as the weighting coefficients w1a to w1d used in the learning operation described above, but may be different.

  As can be seen from FIG. 7, the travel route TR_candidate is set around the travel route TR_actual. For this reason, there is a relatively high possibility that an obstacle existing around the travel route TR_actual coincides with an obstacle present around the travel route TR_candidate. As a result, there is a relatively high possibility that obstacles present around the travel route TR_actual coincide with obstacles present around the target route TR_target. For this reason, selecting the WP information referred to generate the target route TR_target based on the evaluation score SC1 according to the distance between the travel route TR_actual and the obstacle existing around the travel route TR_actual is as follows: This can contribute to generating the target route TR_target so that the distance between the target route TR_target and an obstacle existing around the target route TR_target is relatively large. When the obstacle is a fixed object such as a building, the obstacle existing around the travel route TR_actual should match the obstacle present around the travel route TR_candidate. On the other hand, when the obstacle is a moving body such as another vehicle, the obstacle present around the travel route TR_actual may not match the obstacle present around the travel route TR_candidate.

  Thereafter, the route generation unit 1322 selects one candidate waypoint WP_candidate having the smallest evaluation score SC2 among the plurality of candidate waypoints WP_candidate as the wayway point WP_transit. That is, the route generation unit 1322 passes the start waypoint WP_start or the current position of the vehicle 1 so that the evaluation score SC2 of the target route TR_target that reaches the completion waypoint WP_end via the wayway point WP_transit is minimized. A waypoint WP_transit is set. In other words, the route generation unit 1322 sets the waypoint WP_transit so that the travel route TR_candidate that minimizes the evaluation score SC2 is set to the target route TR_target.

  Thereafter, the route generation unit 1322 should move the vehicle 1 along the travel route that reaches the completed waypoint WP_end included in the waypoint information acquired in step S22 via the wayway point WP_transit set in step S23. It generates as a target route TR_target (step S24). At this time, when it is determined that the driver is requesting execution of the parking assistance operation, if the vehicle 1 is located at or close to the start waypoint WP_start, the route generation unit 1322 performs step S22. A travel route that reaches the completed waypoint WP_end via the wayway point WP_transit is generated as the target route TR_target from the start waypoint WP_start included in the waypoint information acquired in step 1). On the other hand, when the vehicle 1 is not close to the start waypoint WP_start (for example, a predetermined distance or more) at the time when it is determined that the driver requests execution of the parking assistance operation, the route generation unit 1322 generates a travel route that reaches the complete waypoint WP_end from the current position of the vehicle 1 via the wayway point WP_transit as a target route TR_target. In addition, since the operation | movement itself which produces | generates the travel route which the vehicle 1 should move via a specific point may employ | adopt an existing operation | movement, the detailed operation | movement is abbreviate | omitted for the simplification of description.

  Thereafter, the vehicle control unit 1323 generates at step S24 by controlling at least one of a drive source (for example, an engine) of the vehicle 1, a braking device of the vehicle 1, a steering device of the vehicle 1, and a gear mechanism of the vehicle 1. The vehicle 1 is automatically moved along the set target route TR_target (step S25). That is, the vehicle control unit 1323 automatically moves the vehicle 1 so that the vehicle 1 reaches the completion waypoint WP_end from the start waypoint WP_start or the current position of the vehicle 1 via the wayway point WP_transit. In the present embodiment, for convenience of explanation, it is assumed that the vehicle 1 is located at the start waypoint WP_start when it is determined that the driver requests execution of the parking assistance operation. As a result, the vehicle 1 is automatically parked in the parking space SP without requiring the driver to operate the accelerator pedal, the brake pedal, the steering wheel, and the shift lever.

(3) Technical Effects As described above, in this embodiment, in order to automatically park the vehicle 1 in the parking space SP, the learning unit 131 includes the start waypoint WP_start, the shift switching waypoint WP_shift, and the completion way. What is necessary is just to learn the point WP_end. That is, the learning unit 131 may not learn the entire travel route TR_actual on which the vehicle 1 actually traveled while the driver operated the vehicle 1. For this reason, the parking assistance unit 132 reflects the driver's useless operation as compared with the parking assistance unit of the comparative example that generates the target route TR_target based on the learning result of the traveling route TR_actual itself that the vehicle 1 actually traveled. The target route TR_target that is relatively unlikely to be generated can be generated.

  Specifically, FIG. 8 is a plan view showing a travel route TR_actual on which the vehicle 1 actually travels when the vehicle 1 is parked in the parking space SP by the driver's parking operation. As shown in FIG. 4, there is a relatively high possibility that the driver's useless operation is reflected on the travel route TR_actual. The driver's useless operation includes, for example, a steering operation that does not contribute to parking of the vehicle 1 among the steering operations that steer the steered wheels of the vehicle 1. A steering operation that does not contribute to the parking of the vehicle 1 corresponds to a steering operation in which the vehicle can be appropriately parked in the parking space without the steering operation. The steering operation that does not contribute to the parking of the vehicle 1 includes, for example, at least one of a steering operation that steers the steered wheels of the vehicle 1 more than necessary and a steering operation that returns steered wheels that have been steered excessively. Furthermore, when a steering operation that does not contribute to the parking of the vehicle 1 is performed, the position (in other words, the timing) at which the driver switches the gear range is not necessarily optimal. When such a driver's useless operation is reflected in the travel route TR_actual, the driver's useless operation is also reflected in the target route TR_target generated by the parking support unit of the comparative example. Therefore, the parking assistance unit of the comparative example may not be able to generate an appropriate target route TR_target that can park the vehicle 1 in the parking space SP more efficiently.

  On the other hand, FIG. 9 is a plan view showing the target route TR_target generated by the parking assistance unit 132 of the present embodiment. In the present embodiment, as described above, the parking assistance unit 132 generates the target route TR_target based on the start waypoint WP_start, the route waypoint WP_transit, and the completion waypoint WP_end. That is, the parking assistance unit 132 does not generate the target route TR_target based on the travel route TR_actual (particularly, its linear shape). Furthermore, the parking assistance unit 132 generates the target route TR_target using the transit waypoint WP_transit set based on the shift switching waypoint WP_shift instead of directly using the learned shift switching waypoint WP_shift. That is, the parking assistance unit 132 does not necessarily generate the target route TR_target that switches the gear range at the position where the driver switches the gear range. For this reason, the target route TR_target generated by the parking support unit 132 is less likely to reflect a driver's useless operation than the target route TR_target generated by the parking support unit of the comparative example. Therefore, the parking support unit 132 can generate an appropriate target route TR_target that can park the vehicle 1 in the parking space SP more efficiently than the parking support unit of the comparative example. As a result, the parking assist unit 132 can travel the appropriate travel route and park the vehicle 1 in the parking space SP.

  In addition, the learning unit 131 learns the start waypoint WP_start, the shift switching waypoint WP_shift, and the completion waypoint WP_end corresponding to the travel route TR_actual that minimizes the evaluation score SC1. In other words, the learning unit 131 has a waypoint on the travel route TR_actual having a relatively small curvature change rate, a relatively large distance to the obstacle, a relatively small number of times of turning back, and / or a relatively short route. Learn WP. In addition, the parking support unit 132 is a way on the travel route TR_actual having a relatively small curvature change rate, a relatively large distance to the obstacle, a relatively small number of times of turning back, and / or a relatively short route. Based on the learning result of the point WP, a new wayway point WP_transit is set so that the evaluation score SC2 of the target route TR_target is minimized, and a target route TR_target is generated using the wayway point WP_transit. For this reason, the parking assistance unit 132 generates a target route TR_target having a relatively small curvature change rate, a relatively large distance to an obstacle, a relatively small number of times of switching, and / or a relatively short number of times. can do. Therefore, the parking support unit 132 can generate an appropriate target route TR_target that can park the vehicle 1 in the parking space SP more efficiently than the parking support unit of the comparative example. As a result, the parking assist unit 132 can travel the appropriate travel route and park the vehicle 1 in the parking space SP.

  Further, in the present embodiment, the learning unit 131 may not store information related to the learning result of the travel route TR_actual itself. That is, it is sufficient for the learning unit 131 to store information regarding learning results of the start waypoint WP_start, the shift switching waypoint WP_shift, and the completion waypoint WP_end. For this reason, in this embodiment, the information amount which the learning unit 131 memorize | stores compared with a comparative example. For this reason, the load required for storing information by the learning unit 131 can be reduced.

(4) Modified Examples Hereinafter, modified examples of the learning operation and the parking assist operation will be described.

(4-1) First modification
(4-1-1) Learning Operation in the First Modification First, the learning operation in the first modification will be described with reference to FIG. FIG. 10 is a flowchart showing the flow of the learning operation in the first modification.

  As shown in FIG. 6, also in the first modified example, the learning unit 131 performs the processing from step S11 to step S15. In the first modified example, the learning unit 131 further specifies the straight travel start waypoint WP_st1 and the straight travel end waypoint WP_st2 based on the detection information detected in step S12 (step S31). The straight start start waypoint WP_st1 corresponds to the position of the vehicle 1 at the timing when the period during which the straight drive operation contributing to the parking of the vehicle 1 is performed by the driver has started. That is, the straight start start point WP_st1 corresponds to the position of the vehicle 1 at the timing when the driver starts the straight drive operation that contributed to the parking of the vehicle 1. The straight travel end waypoint WP_st2 corresponds to the position of the vehicle 1 at the timing when the period during which the straight drive operation contributing to the parking of the vehicle 1 is performed by the driver is completed. That is, the straight travel end waypoint WP_st2 corresponds to the position of the vehicle 1 at the timing when the driver finishes the straight travel operation that contributed to the parking of the vehicle 1.

  The straight traveling operation is an operation for causing the vehicle 1 to travel straight. The straight traveling operation is typically performed while the steered wheel is slightly steered to the extent that the vehicle 1 moves straight in a state where the steered wheel is in a neutral state (that is, the vehicle in a state where the steered angle is substantially zero). This is an operation for moving the vehicle 1 forward or backward (with fine adjustment of the turning angle to the extent that 1 is moved straight). The straight-ahead operation that has contributed to the parking of the vehicle 1 corresponds to a straight-ahead operation in which the vehicle 1 cannot be properly parked in the parking space SP unless the straight-ahead operation is performed. In other words, the straight-ahead operation that contributed to the parking of the vehicle is a travel route that is not appropriate for parking the vehicle 1 in the parking space SP unless the straight-ahead operation is performed (for example, a travel route that is longer than necessary and bent more than necessary). This corresponds to a straight-ahead operation that must pass through at least one of the travel routes. Accordingly, the straight-ahead operation that contributes to the parking of the vehicle 1 substantially corresponds to a straight-ahead operation necessary for appropriately parking the vehicle 1 in the parking space SP. In other words, the straight-ahead operation that contributes to the parking of the vehicle 1 corresponds to a straight-ahead operation other than the straight-ahead operation that does not contribute to the parking of the vehicle 1. A straight-ahead operation that does not contribute to the parking of the vehicle 1 corresponds to a straight-ahead operation that allows the vehicle 1 to be appropriately parked in the parking space SP even if the straight-ahead operation is not performed. That is, the straight-ahead operation that does not contribute to the parking of the vehicle 1 is substantially a straight-ahead operation that is unnecessary in order to properly park the vehicle 1 in the parking space SP (in other words, a wasteful straight-ahead operation). It corresponds to.

  Note that the period during which the straight-ahead operation is performed does not include the period during which the steering operation is performed. That is, when the turning operation is performed, the straight traveling operation is performed after the turning operation is completed. Similarly, when the straight traveling operation is performed, the steering operation is performed after the straight traveling operation is completed. For this reason, the straight traveling start waypoint WP_st1 is equivalent to the position of the vehicle 1 at the timing when the period during which the turning operation is performed by the driver is completed. Similarly, the straight travel end waypoint WP_st2 is equivalent to the position of the vehicle 1 at the timing when the period during which the steering operation is performed by the driver is started.

  Hereinafter, an operation for specifying the straight start start waypoint WP_st1 and the straight advance end waypoint WP_st2 will be described with reference to FIGS. 11 and 12A to 12E. FIG. 11 is a flowchart showing a flow of operations for specifying the straight travel start waypoint WP_st1 and the straight travel end waypoint WP_st2. Each of FIG. 12A to FIG. 12E is a graph showing the curvature of the travel route TR_actual.

  As shown in FIG. 11, the WP learning unit 1311 extracts a route portion TR1 in which the absolute value of the curvature is less than a predetermined threshold value TH1 (where TH1 is a positive number) from the travel route TR_actual (step S311). . For example, when the curvature of the travel route TR_actual changes as shown in FIG. 12A, the WP learning unit 1311 has a curvature smaller than + TH1 and −TH1 as shown by a thick solid line in FIG. A plurality of route portions TR1 (specifically, route portion TR1-8 to route portion TR1-8) are extracted. FIG. 12B shows an example in which a plurality of route portions TR1 are extracted. However, a single route portion TR1 may be extracted or the route portion TR1 may not be extracted. .

  When the absolute value of the curvature is larger than the threshold value TH1 (that is, relatively large), the absolute value of the curvature contributes to parking of the vehicle 1 as compared with the case where the absolute value of the curvature is smaller than the threshold value TH1 (that is, relatively small). There is a high possibility that the steering operation is performed. For this reason, during the period in which the absolute value of the curvature is greater than the threshold value TH1, the possibility that the steering operation that contributed to the parking of the vehicle 1 was performed by the driver is relatively high. Note that the steering operation that contributes to the parking of the vehicle 1 is a steering operation other than the steering operation that does not contribute to the parking of the vehicle 1 described above among the steering operations. In other words, during the period in which the absolute value of the curvature is smaller than the threshold value TH1, there is a relatively high possibility that the driver has performed a straight-ahead operation that has contributed to the parking of the vehicle 1. For this reason, the WP learning unit 1311 can appropriately specify (in other words, separate) the straight-ahead operation and the steering operation based on the curvature.

  In consideration of the reason for determining the magnitude relationship between the threshold value TH1 and the curvature of the travel route TR_actual, the threshold value TH1 distinguishes the straight operation and the turning operation from the curvature of the travel route of the vehicle 1. Is preferably set to an appropriate value.

  On the other hand, even if the length of the path portion TR1 is relatively short even if the absolute value of the curvature is smaller than the threshold value TH1, in the path portion TR1, the unnecessary turning of the steered wheels is repeated. Therefore, there is a relatively high possibility that the steering wheel is only operated to return the steered wheels to the neutral state. That is, in the route portion TR1 where the absolute value of the curvature is smaller than the threshold value TH1 and the length is relatively short, there is a relatively high possibility that the driver has performed a straight operation that does not contribute to the parking of the vehicle 1. .

  Therefore, the WP learning unit 1311 excludes the route portion TR1 whose length is shorter than the predetermined threshold value TH2 from the route portion TR1 extracted in step S311 (step S312). For example, when the route portion TR1-8 is extracted from the route portion TR1-1 indicated by the thick solid line in FIG. 12B in step S311, the WP learning unit 1311, as shown in FIG. Four path portions TR1-2, TR1-3, TR1-6, and TR1-8 whose length is shorter than the threshold value TH2 are excluded. As a result of step S312, the WP learning unit 1311 has extracted the path portion TR1 whose absolute value of curvature is less than the threshold value TH1 and whose length is longer than the threshold value TH2. As a result, the WP learning unit 1311 can appropriately identify the route portion TR1 corresponding to the period during which the straight-ahead operation that contributed to the parking of the vehicle 1 was performed based on not only the curvature but also the length.

  Considering the reason for determining the magnitude relationship between the threshold value TH2 and the length of the route portion TR1, the threshold value TH2 does not contribute to the straight-ahead operation that contributes to the parking of the vehicle 1 and the parking of the vehicle 1. It is preferable that the straight operation is set to an appropriate value that can be distinguished from the length of the route portion TR1.

  Thereafter, the WP learning unit 1311 has a predetermined length TH3 (provided that the threshold TH3 is positive) in the route part TR1 extracted in step S311 (excluding the route part TR1 excluded in step S312). It is determined whether there are two path portions TR1 adjacent to each other with an interval of less than (number) (step S313). That is, the travel route TR_actual is divided into the route portion TR1 and the route portion TR2 other than the route portion TR1 (that is, the route portion TR2 whose absolute value of curvature is greater than the threshold value TH1 or whose length is less than the threshold value TH2). In this case, the WP learning unit 1311 determines whether or not there are two adjacent route portions TR1 with the length of the route portion TR2 that is less than the threshold value TH3 being interposed therebetween (step S313).

  As a result of the determination in step S313, when there are two adjacent route portions TR1 (hereinafter referred to as one route portion TR1 and another route portion TR1) that are adjacent to each other with a route portion TR2 having a length less than the threshold TH3. If the determination is made (step S313: Yes), the vehicle travels straight ahead that contributes to the parking of the vehicle 1 performed on one route portion TR1 and the vehicle travels straight to contribute to the parking of the vehicle 1 performed on another route portion TR1. It is presumed that the operation was performed without much time. In this case, the straight-ahead operation performed in one route portion TR1 and the straight-ahead operation performed in another route portion TR1 are almost problematic even if they are handled as a series of straight-ahead operations that contribute to the parking of the vehicle 1. Should not occur. Therefore, the WP learning unit 1311 sets a route portion obtained by integrating the two route portions TR1 together with the route portion TR2 sandwiched therebetween as a new one route portion TR1 (step S314). For example, when the path portions TR1-1, TR1-4, TR1-5, and TR1-7 indicated by thick solid lines in FIG. 12C remain, the WP learning unit 1311 performs the processing shown in FIGS. As shown in d), the route portion TR1-4 and the route portion TR1-5 are integrated with the route portion TR2 located between the route portion TR1-4 and the route portion TR1-5 to form a new route portion TR1. Set to -9.

  After that, the WP learning unit 1311 identifies the position corresponding to the starting end of the finally remaining route portion TR1 as the straight travel start waypoint WP_st1 (step S315). The WP learning unit 1311 specifies a position corresponding to the end of the extracted route portion TR1 as the straight travel end waypoint WP_st2 (step S315). For example, when the route portions TR1-1, TR1-7, and TR1-9 indicated by thick solid lines in FIG. 12E remain, the WP learning unit 1311 performs the route portions TR1-1, TR1-7, and TR1. A position corresponding to the start end of each of −9 is specified as a straight travel start waypoint WP_st1. Furthermore, the WP learning unit 1311 specifies a position corresponding to the end of each of the route portions TR1-1, TR1-7, and TR1-9 as the straight travel end waypoint WP_st2. An example of the relationship between the straight travel start waypoint WP_st1 and the straight travel end waypoint WP_st2 and the travel route TR_actual shown in FIG. 12 (e) is shown in FIG.

  In FIG. 10 again, the WP learning unit 1311 receives WP information including a set of information of the learned start waypoint WP_start, shift switching waypoint WP_shift, completion waypoint WP_end, straight start start point WP_st1, and straight end point WP_st2. It memorize | stores in the memory | storage part 1312 (step S18). However, when it is determined that WP information acquired in the past has already been stored in the WP storage unit 1312 (step S16: Yes), the WP learning unit 1311 evaluates the new WP information and the old WP information sound. The WP information having the smaller score SC1 (that is, the smallest) is stored in the WP storage unit 1312 (step S17).

(4-1-2) Parking Support Operation in the First Modification Example Next, the parking support operation in the first modification example will be described with reference to FIG. FIG. 14 is a flowchart showing a flow of the parking support operation in the first modification.

  As shown in FIG. 14, also in the first modified example, the parking support unit 132 performs the processing from step S21 to step S22.

  Thereafter, the route generation unit 1322 sets the waypoint WP_transit based on the shift switching waypoint WP_shift, the straight start start point WP_st1, and the straight end point WP_st2 included in the WP information acquired in Step S22 (Step S43). ). Specifically, the route generation unit 1322 sets the first waypoint WP_transit1 based on the shift switching waypoint WP_shift. Further, the route generation unit 1322 uses a method similar to the method of setting the first waypoint WP_transit1 based on the shift switching waypoint WP_shift, and uses the second wayway point based on the straight start start point WP_st1. Set WP_transit2. Further, the route generation unit 1322 uses a method similar to the method of setting the first waypoint WP_transit1 based on the shift switching waypoint WP_shift, and uses the second wayway point based on the straight start start point WP_st1. Set WP_transit2. That is, the route generation unit 1322 sets the first waypoint WP_transit3 from the first waypoint WP_transit3 so that the evaluation score SC2 is minimized. However, in the first modified example, the evaluation score SC2 is the first candidate waypoint that is a candidate for the first wayway point WP_transit1 to the third wayway point WP_transit3 from the start waypoint WP_start or the current position of the vehicle 1. This is a quantitative index value indicating the optimum degree of the travel route TR_candidate that reaches the completion waypoint WP_end from WP_candidate1 via the third candidate waypoint WP_candidate3.

  After that, the route generation unit 1322 starts from the first way waypoint WP_transit1 set in step S43 from the start waypoint WP_start included in the waypoint information acquired in step S22 or the current position of the vehicle 1 to the third way way. A travel route that reaches the complete waypoint WP_end included in the waypoint information acquired in step S22 via the point WP_transit3 is generated as a target route TR_target that the vehicle 1 should travel (step S24). Thereafter, the vehicle control unit 1323 automatically moves the vehicle 1 along the target route TR_target generated in step S24 (step S25).

(4-1-3) Technical Effects of the First Modification According to the learning operation and the parking support operation in the first modification described above, the effects that can be enjoyed by the learning operation and the parking support operation of the present embodiment described above. You can enjoy the same effect.

  Furthermore, in the first modified example, when the target route TR_target is generated in order to reflect the route portion TR1 on which the straight-ahead operation that has contributed to the parking of the vehicle 1 is performed, on the target route TR_target, the straight-start start waypoint WP_st1 The end waypoint WP_st2 is used. For this reason, the route generation unit 1322 generates a more appropriate target route TR_target (particularly, an appropriate target route TR_target that excludes the influence of useless steering operation) in consideration of the straight-ahead operation that has contributed to the parking of the vehicle 1. be able to.

  Furthermore, when two adjacent route portions TR1 are integrated with a route portion TR2 having a length less than the third threshold TH3, the number of route portions TR1 remaining finally decreases. For this reason, the total number of straight start start point WP_st1 and straight end point WP_st2 also decreases. For this reason, the path | route production | generation part 1322 can produce | generate the more efficient target path | route TR_target which excluded the influence of useless steering operation much more.

(4-2) Second Modification As described above, after the target route TR_target is generated, the vehicle control unit 1323 automatically moves the vehicle 1 along the target route TR_target. That is, the vehicle control unit 1323 automatically parks the vehicle 1 in the parking space SP according to the target route TR_target. However, for some reason, as shown in FIG. 15A, the vehicle 1 traveling under the control of the vehicle control unit 1323 may deviate from the target route TR_target. In other words, the actual travel route TR_assist of the vehicle 1 traveling under the control of the vehicle control unit 1323 may deviate from the target route TR_target. In this case, there is a possibility that the vehicle 1 cannot be properly parked in the parking space SP.

  Therefore, in the second modification, the route generation unit 1322 determines whether or not the vehicle 1 traveling under the control of the vehicle control unit 1323 deviates from the target route TR_target by a predetermined amount or more. That is, the route generation unit 1322 determines whether or not the travel route TR_assist has deviated from the target route TR_target by a predetermined amount or more. When it is determined that the travel route TR_assist has deviated from the target route TR_target by a predetermined amount or more, the route generation unit 1322 generates a new target route TR_target 'as illustrated in FIG. Specifically, the route generation unit 1322 sets a new route waypoint WP_transit ′ to be routed by the new target route TR_target ′ based on the route waypoint WP_transit that has already been set. The operation of setting a new via waypoint WP_transit 'based on the already set via waypoint WP_transit is the same as the operation of setting the viaway waypoint WP_transit based on the shift switching waypoint WP_shift. Is omitted. Thereafter, the route generation unit 1322 generates, as a new target route TR_target ', a travel route that reaches the completion waypoint WP_end from the current position of the vehicle 1 via the new waypoint WP_transit'. As a result, even if the vehicle 1 traveling under the control of the vehicle control unit 1323 deviates from the target route TR_target by a predetermined amount or more, the parking support unit 132 causes the vehicle 1 to travel along an appropriate traveling route. The parking space SP can be parked.

(4-3) Other Modifications In the above description, in step S23 in FIG. 6, the route generation unit 1322 sets a plurality of candidate waypoints WP_candidate in the predetermined area CA, and then sets a plurality of candidate waypoints WP_candidate. Any one of them is selected as the waypoint WP_transit. However, in addition to or instead of setting a plurality of candidate waypoints WP_candidate, the route generation unit 1322 determines the wayway point WP_transit that minimizes the evaluation score SC2 using the nonlinear minimum method or the like in the predetermined area CA. You may search.

  In the above description, in step S23 of FIG. 6, the route generation unit 1322 sets the waypoint WP_transit so that the evaluation score SC2 is minimized. However, if the evaluation score SC2 is reduced to some extent, the target route TR_target via the waypoint WP_transit corresponding to the evaluation score SC2 is appropriately appropriate (that is, the vehicle 1 is placed in the parking space SP along the target route TR_target). If it is parked, there is a possibility that useless driving is relatively reduced). For this reason, the route generation unit 1322 allows the evaluation score SC2 to be equal to or less than a predetermined first threshold that can distinguish the state where the target route TR_target is appropriate and the state where the target route TR_target is not appropriate from the evaluation score SC2. A waypoint WP_transit may be set.

  In the above description, in step S <b> 17 of FIG. 2, the WP learning unit 1311 stores only one WP information having a smaller evaluation score SC <b> 1 (that is, the smallest) in the WP storage unit 1312. However, the WP learning unit 1311 may store a plurality of WP information in the WP storage unit 1312. For example, if the evaluation score SC1 is small to some extent, the travel route TR_actual corresponding to the evaluation score SC1 is appropriately appropriate (that is, it may be referred to when calculating the target route TR_target in the parking assistance operation). is there. For this reason, the WP learning unit 1311 has a plurality of pieces of WP information in which the evaluation score SC1 is equal to or less than a predetermined second threshold that can distinguish the state where the travel route TR_actual is appropriate and the state where the travel route TR_actual is not appropriate from the evaluation score SC1. May be stored in the WP storage unit 1312. When a plurality of WP information is stored in the WP storage unit 1312, in step S23 of FIG. 6, the path generation unit 1322 includes a predetermined area CA including a plurality of shift switching waypoints WP_shift included in the plurality of WP information. A plurality of candidate waypoints WP_candidate may be set therein.

  In the above description, the evaluation score SC2 is defined so that the evaluation score SC2 becomes smaller as the travel route TR_candidate becomes appropriate. However, the evaluation score SC2 may be defined such that the evaluation score SC2 increases as the travel route TR_candidate becomes appropriate. In this case, in step S23 of FIG. 6, the route generation unit 1322 may set the waypoint WP_transit so that the evaluation score SC2 becomes large (that is, maximizes). Alternatively, the route generation unit 1322 causes the wayway so that the evaluation score SC2 is equal to or higher than a predetermined third threshold that can distinguish the state where the target route TR_target is appropriate and the state where the target route TR_target is not appropriate from the evaluation score SC2. The point WP_transit may be set.

  Similarly, in the above description, the evaluation score SC1 is defined such that the evaluation score SC1 decreases as the travel route TR_actual becomes appropriate. However, the evaluation score SC1 may be defined such that the evaluation score SC1 increases as the travel route TR_actual becomes appropriate. In this case, in step S17 of FIG. 2, the WP learning unit 1311 may cause the WP storage unit 1312 to store the WP information having the larger evaluation score SC1 (that is, the maximum). Alternatively, the WP learning unit 1311 obtains a plurality of pieces of WP information in which the evaluation score SC1 is equal to or greater than a predetermined fourth threshold value that can distinguish the state where the travel route TR_actual is appropriate and the state where the travel route TR_actual is not appropriate from the evaluation score SC1. , It may be stored in the WP storage unit 1312.

  In the above description, in the learning operation, the WP learning unit 1311 calculates the evaluation score SC1, and causes the WP storage unit 1322 to store WP information in which the evaluation score SC1 is minimum (or is equal to or less than the first threshold value). ing. However, the WP learning unit 1311 may store the acquired WP information in the WP storage unit 1322 without calculating the evaluation score SC1. In this case, in the parking support operation, the route generation unit 1322 calculates the evaluation score SC1 corresponding to the WP information stored in the WP storage unit 1322, and the WP storage unit 1322 calculates the evaluation score SC1 based on the calculated evaluation score SC1. From the stored WP information, at least one WP information to be referred to in order to generate the target route TR_target may be selected. For example, the route generation unit 1322 may select the WP information that minimizes the evaluation score SC1.

  In the above description, the learning unit 131 learns at least one of the shift switching waypoint WP_shift, the straight start start point WP_st1, and the straight end point WP_st2 in order to set the via waypoint WP_transit. The shift switching waypoint WP_shift is the position of the vehicle 1 at the shift switching timing when the driver switches the gear range in order to park the vehicle 1 (that is, the timing at which the traveling direction of the vehicle 1 is switched). The straight travel start waypoint WP_st1 and the straight travel end waypoint WP_st2 are respectively the timing at which the period during which the driver performs a straight traveling operation to park the vehicle 1 and the timing at which the period has ended (that is, the period during which the vehicle 1 travels straight). Is the position of the vehicle 1 at the timing of starting and ending. Therefore, any of the above-described waypoints WP used for setting the waypoint WP_transit corresponds to the position of the vehicle 1 when the behavior of the vehicle 1 becomes a predetermined behavior that contributes to the parking of the vehicle 1. . In this case, the learning unit 131 contributes to the parking of the vehicle 1 in addition to or instead of at least one of the shift switching waypoint WP_shift, the straight start start waypoint WP_st1, and the straight advance end waypoint WP_st2. You may learn the position of the vehicle 1 at the time of becoming a predetermined behavior as the waypoint WP for setting the wayway point WP_transit. Further, the route generation unit 1322 may set the waypoint WP_transit based on the learned waypoint WP in the same manner as the operation of setting the wayway point WP_transit based on the shift switching waypoint WP_shift or the like.

  In the above description, the evaluation score SC1 depends on the curvature change rate of the travel route TR_actual, the distance between the travel route TR_actual and the obstacle, the number of turn-overs in the vehicle 1 traveling on the travel route TR_actual, and the length of the travel route TR_actual. The index value is determined by However, the evaluation score SC1 is at least one of the curvature change rate of the travel route TR_actual, the distance between the travel route TR_actual and the obstacle, the number of times of turning in the vehicle 1 traveling on the travel route TR_actual, and the length of the travel route TR_actual. It may be an index value unrelated to one. For example, the evaluation score SC1 is determined according to the curvature change rate of the travel route TR_actual and the distance between the travel route TR_actual and the obstacle, while the number of turn-backs in the vehicle 1 traveling on the travel route TR_actual and the length of the travel route TR_actual. It may be an index value unrelated to Sato. The same applies to the evaluation score SC2.

  The evaluation score SC1 is at least one of the curvature change rate of the travel route TR_actual, the distance between the travel route TR_actual and the obstacle, the number of times the vehicle 1 travels on the travel route TR_actual, and the length of the travel route TR_actual. In addition or alternatively, an index value determined according to other parameters may be used. For example, the evaluation score SC1 may be an index value that is determined according to the time required for the vehicle 1 to travel on the travel route TR_actual. Specifically, the evaluation score SC1 may be, for example, an index value determined from the viewpoint that the travel route TR_actual is appropriate as the time required for the vehicle 1 to travel on the travel route TR_actual is shortened. Alternatively, for example, the evaluation score SC1 may be an index value determined according to the vehicle speed of the vehicle 1 traveling on the travel route TR_actual. Specifically, the evaluation score SC1 is, for example, a viewpoint that the travel route TR_actual is appropriate when the curvature of the travel route TR_actual increases and / or the vehicle speed decreases as the distance between the vehicle 1 and the obstacle decreases. It may be an index value determined from Alternatively, for example, the evaluation score SC1 may be an index value determined according to the attitude of the vehicle 1 at the time of parking completion (for example, an angle with respect to the parking space SP). Specifically, the evaluation score SC1 may be, for example, an index value determined from the viewpoint that the travel route TR_actual is appropriate as the posture of the vehicle 1 at the time of completion of parking approaches the posture that matches the parking space SP. . The same applies to the evaluation score SC2.

  The weighting coefficients w1a to w1d and w2a to w2d used for calculating the evaluation scores SC1 and SC2 may be set based on the evaluation from the driver for the target route TR_target generated by the route generation unit 1322. For example, when the evaluation from the driver for the target route TR_target is accumulated, whether the driver attaches importance to the curvature change rate of the target route TR_target or not between the target route TR_target and the obstacle based on the accumulated evaluation. It is possible to determine the tendency of whether the importance is placed on the distance, the number of times of turnover, and / or the length of the target route TR_target. Therefore, the learning unit 131 and / or the parking unit 132 determines which parameter the driver tends to emphasize based on the evaluation from the driver with respect to the target route TR_target, and corresponds to the parameter emphasized. The weighting factor may be increased.

(5) Additional notes The following additional notes are disclosed with respect to the embodiment described above.

(5-1) Appendix 1
The parking assist device according to attachment 1 learns a specific position that is a position of the vehicle when a behavior of the vehicle satisfies a specific condition during a period in which a driver performs a parking operation for parking the vehicle. Learning means, a setting means for setting a via position within a first predetermined range including the specific position learned by the learning means, and the vehicle parked via the via position set by the setting means. Generating means for generating a first travel route that reaches a target position to be ended as a target route through which the vehicle passes when the vehicle is automatically parked at the target position; The first of the first travel routes determined in accordance with at least the curvature change rate of the first travel route and / or the distance between the first travel route and the first obstacle existing around the first travel route. Evaluation score Based on a parking assist apparatus characterized by setting the via location.

  According to the parking assistance apparatus described in attachment 1, the learning unit may learn the specific position. That is, the learning means does not have to learn the travel route itself on which the vehicle actually traveled during the period when the parking operation is performed by the driver. In addition, based on the first evaluation score, the setting means can set the via position that the actual target route should pass through to the first predetermined range including the specific position. For this reason, the parking assistance apparatus according to Supplementary Note 1 includes a parking assistance apparatus according to a comparative example that generates a target route based on a learning result of a traveling route itself that the vehicle actually traveled during a period in which the parking operation is performed by the driver. In comparison, it is possible to generate a target route that is relatively less likely to reflect a driver's useless operation. That is, the parking assistance device described in Supplementary Note 1 can generate an appropriate target route that can more efficiently park the vehicle in the parking space than the parking assistance device of the comparative example. As a result, the parking assistance device described in Supplementary Note 1 can drive the appropriate travel route and park the vehicle in the parking space.

(5-2) Appendix 2
In the parking assistance device according to attachment 2, the first evaluation score decreases as the curvature change rate of the first travel route decreases and / or the distance between the first travel route and the first obstacle. The setting position is set so that the first evaluation score is less than or equal to a predetermined first threshold value or the minimum value. Parking assistance device.

  According to the parking assistance apparatus described in appendix 2, the setting unit is configured such that the curvature change rate of the target route is relatively small and / or the distance between the target route and the first obstacle is relatively large. In addition, the via position can be set.

  The first evaluation score may increase as the curvature change rate of the first travel route decreases and / or increase as the distance between the first travel route and the first obstacle increases. The setting unit may set the via position so that the first evaluation score is equal to or higher than a predetermined third threshold value. Even in this case, the setting means sets the via position so that the curvature change rate of the target route is relatively small and / or the distance between the target route and the first obstacle is relatively large. Can be set.

(5-3) Appendix 3
The parking assist device according to attachment 3, wherein the specific position is the position of the vehicle at the time when the gear range of the vehicle is switched, and a straight-ahead operation for causing the vehicle to go straight so as to contribute to the parking of the vehicle. At least one of the position of the vehicle at the start of a period that has been performed as part of the operation and the position of the vehicle at the end of the period in which the rectilinear operation has been performed as part of the parking operation. It is a parking assistance apparatus as described in any one of the supplementary notes 1 to 3 characterized by including one.

  According to the parking assist device of appendix 3, the setting means is configured to pass through the specific position corresponding to the position of the vehicle when the behavior of the vehicle becomes a predetermined behavior that contributes to parking of the vehicle. The position can be set.

(5-4) Appendix 4
When the parking operation is performed at least twice by the driver, the setting unit is configured such that the setting unit has at least two specific positions respectively corresponding to the at least two parking operations. At least the curvature change rate of the second travel route traveled by the vehicle by each parking operation and / or the distance between the second travel route and the second obstacle existing around the second travel route. Any one of Supplementary notes 1 to 4, wherein the via position is set within the first predetermined range including a desired specific position selected based on a second evaluation score determined for each parking operation. It is the parking assistance apparatus of description.

  According to the parking assistance apparatus described in appendix 4, the setting unit can appropriately set the via position even when the parking operation is performed at least twice by the driver.

(5-5) Appendix 5
In the parking assistance device according to attachment 5, the second evaluation score decreases as the curvature change rate of the second travel route decreases and / or the distance between the second travel route and the second obstacle. And the desired specific position becomes smaller than a predetermined second threshold value among the at least two second travel routes respectively corresponding to the at least two parking operations. The parking assist device according to appendix 4, wherein the specific position corresponds to a minimum desired second travel route.

  According to the parking assistance device described in appendix 5, if the transit position is set using the second travel route in which the curvature change rate of the second travel route is relatively small, the curvature change rate of the target route is also relative. There is a high possibility that it will become smaller. Further, the second obstacle existing around the second travel route on which the vehicle actually traveled until reaching the target position, and the first travel route generated by the generating means for generating the target route reaching the target position. There is a high possibility that the first obstacle present in the vicinity coincides at least partially. For this reason, if the via position is set using the second travel route in which the distance between the second travel route and the second obstacle is relatively large, the distance between the target route and the first obstacle Are also likely to be relatively large. For this reason, the setting means may set the via position so that the curvature change rate of the target route becomes relatively small and / or the distance between the target route and the first obstacle becomes relatively large. it can.

  The second evaluation score may increase as the curvature change rate of the second travel route decreases and / or increase as the distance between the second travel route and the second obstacle increases. The setting means is a first one in which the second evaluation score is greater than or equal to a predetermined fourth threshold value among the at least two second travel routes on which the vehicle has traveled in the at least two parking operations. The via position may be set within the first predetermined range including the specific position corresponding to two travel routes. Even in this case, the setting means sets the via position so that the curvature change rate of the target route is relatively small and / or the distance between the target route and the first obstacle is relatively large. Can be set.

(5-6) Appendix 6
The parking support apparatus according to attachment 6, wherein the setting unit has deviated from the target route by a predetermined amount or more during a period in which the vehicle is automatically parked according to the target route generated by the generating unit. Based on the above, based on the first evaluation score, a new route position is set within a second predetermined range including the route position that has already been set. When the position is set, the first travel route that reaches the target position via the new via position set by the setting unit is generated as the new target route. The parking assist device according to any one of appendices 1 to 5.

  According to the parking assistance device of appendix 6, when the vehicle deviates from the target route by a predetermined amount or more, the generation means has a relatively small curvature change rate and / or a first obstacle. A new target route with a relatively large distance can be appropriately generated.

  The present invention can be appropriately changed without departing from the gist or the idea of the invention that can be read from the claims and the entire specification, and a parking assisting device with such a change is also included in the technical idea of the present invention. .

DESCRIPTION OF SYMBOLS 1 Vehicle 11 External field detection apparatus 12 Internal field detection apparatus 13 ECU
131 learning unit 1311 WP learning unit 1312 WP storage unit 132 parking support unit 1321 information acquisition unit 1322 route generation unit 1323 vehicle control unit TR_actual, TR_candidate travel route TR_target target route WP waypoint WP_start start waypoint WP_sway waypoint WP_s Point WP_st1 Straight start start waypoint WP_st2 Straight finish end waypoint WP_transit waypoint WP_candidate waypoint SP Parking space

Claims (6)

Learning means for learning a specific position that is a position of the vehicle at a time when the behavior of the vehicle satisfies a specific condition during a period in which a parking operation for parking the vehicle is performed by a driver;
Setting means for setting a via position within a first predetermined range including the specific position learned by the learning means;
When the vehicle automatically parks the vehicle at the target position on the first travel route that reaches the target position where the vehicle should end parking via the via position set by the setting means. Generating means for generating as a target route to be passed,
The setting means is determined in accordance with at least a curvature change rate of the first travel route and / or a distance between the first travel route and a first obstacle existing around the first travel route. The parking assistance device, wherein the route position is set based on a first evaluation score of a travel route. The first evaluation score decreases as the curvature change rate of the first travel route decreases and / or decreases as the distance between the first travel route and the first obstacle increases.
The parking support device according to claim 1, wherein the setting unit sets the via position so that the first evaluation score is equal to or less than a predetermined first threshold value. The specific position is the position of the vehicle at the time when the gear range of the vehicle is switched, and the period during which a straight-ahead operation for moving the vehicle straight so as to contribute to the parking of the vehicle is performed as part of the parking operation. The position of the vehicle at the start time of the vehicle, and at least one of the position of the vehicle at the end of a period during which the straight-ahead operation is performed as part of the parking operation are included. Parking assistance device. When the parking operation is performed at least twice by the driver, the setting means is configured to at least each of the two specific positions corresponding to the at least two parking operations. The second evaluation determined for each parking operation according to the curvature change rate of the second travel route on which the vehicle traveled and / or the distance between the second travel route and the second obstacle existing around the second travel route. The parking assistance device according to any one of claims 1 to 3, wherein the via position is set within the first predetermined range including a desired specific position selected based on a score. The second evaluation score decreases as the curvature change rate of the second travel route decreases and / or decreases as the distance between the second travel route and the second obstacle increases.
The desired specific position is a desired value at which the second evaluation score is less than or equal to a predetermined second threshold value among at least two second travel routes on which the vehicle has traveled in the at least two parking operations. The parking assistance device according to claim 4, wherein the specific position corresponds to the second travel route. The setting means has the first evaluation score on the condition that the vehicle deviates from the target route by a predetermined amount or more during a period in which the vehicle is automatically parked according to the target route generated by the generating unit. Based on the above, a new via position is set within the second predetermined range including the already set via position,
The generating means, when the setting means sets the new via position, the first travel route that reaches the target position via the new via position set by the setting means, It generates as the new said target route. The parking assistance apparatus as described in any one of Claim 1 to 5 characterized by the above-mentioned.

Images